 kijai
|
ceb4bb50cf
|
Update nodes.py
|
2025-04-01 13:51:41 +03:00 |
|
|
kijai
|
23c9a6d634
|
Add dynamo_recompile_limit as adjustable option, revert to old euler for flowedit
|
2025-04-01 11:44:45 +03:00 |
|
|
kijai
|
40f1ea730c
|
autoscale temporal mask better
|
2025-03-31 22:27:50 +03:00 |
|
|
Jukka Seppänen
|
9100eecccf
|
Merge pull request #354 from xStrom/clipvision
Load clip vision models from the `clip_vision` folder.
|
2025-03-31 12:15:58 +03:00 |
|
|
Jukka Seppänen
|
0c9a346ef6
|
Merge pull request #358 from green-s/patch-1
Fix typo
|
2025-03-31 12:13:20 +03:00 |
|
|
Sam Green
|
81c640d758
|
Fix typo
|
2025-03-31 02:13:39 +01:00 |
|
|
kijai
|
2b1315f80c
|
Update nodes.py
|
2025-03-31 03:33:25 +03:00 |
|
|
kijai
|
999394ed09
|
Allow custom temporal masks for Fun InP model
|
2025-03-31 02:36:36 +03:00 |
|
|
kijai
|
91f0ccc594
|
revert this
|
2025-03-31 01:51:49 +03:00 |
|
|
kijai
|
fe9fb7e2f0
|
Only use custom preview code for TAEW
|
2025-03-31 01:25:37 +03:00 |
|
|
kijai
|
7a3f064a2c
|
Update nodes.py
|
2025-03-30 23:17:42 +03:00 |
|
|
kijai
|
facf65aec6
|
Allow using more than one start_image with the Fun InP models
|
2025-03-30 23:06:28 +03:00 |
|
|
Kaur Kuut
|
1b64f0e6d8
|
Add support for selecting clip models from text_encoders.
|
2025-03-30 18:30:36 +03:00 |
|
|
kijai
|
4970f84f5f
|
Update wan_video_vae.py
|
2025-03-30 16:17:17 +03:00 |
|
|
Jukka Seppänen
|
0291b5205c
|
Merge pull request #353 from xStrom/vaeopt
Add validation and documentation to VAE tiling.
|
2025-03-30 16:01:12 +03:00 |
|
|
Kaur Kuut
|
9c6cd86d5e
|
Load clip vision models from the clip_vision folder.
|
2025-03-30 15:32:24 +03:00 |
|
|
Kaur Kuut
|
8fafa236fd
|
Add validation and documentation to VAE tiling.
|
2025-03-30 14:34:19 +03:00 |
|
|
kijai
|
0cf1330928
|
Make tiled VAE actually work...
Still only really necessary at very high resolutions
|
2025-03-30 01:21:05 +02:00 |
|
|
kijai
|
7f1446b7aa
|
Fix flowedit
|
2025-03-29 14:13:53 +02:00 |
|
|
kijai
|
58e464d33a
|
bump version
|
2025-03-28 13:39:38 +02:00 |
|
|
kijai
|
6334dfab84
|
Make start_image optional for Fun-InP workflows, fix control lora
NOTE the ImageToVideo encode node inputs end up changing getting mixed up due to the change, old workflows need resetting those inputs.
|
2025-03-28 13:10:52 +02:00 |
|
|
kijai
|
d9b1f4d1a5
|
fix control if start percent set
|
2025-03-28 02:08:40 +02:00 |
|
|
kijai
|
104c632359
|
some cleanup
|
2025-03-28 01:58:47 +02:00 |
|
|
kijai
|
2d56d69ccb
|
Add alternative TeaCache mode, better frame matching for control workflow
Based on the coefficients from here:
https://github.com/ali-vilab/TeaCache/pull/51
|
2025-03-27 19:44:37 +02:00 |
|
|
kijai
|
ccca41cdb7
|
Update wanvideo_Fun_control_example_01.json
|
2025-03-27 14:31:54 +02:00 |
|
|
kijai
|
cdd48c7490
|
Fix control model link, add better error
|
2025-03-27 14:27:17 +02:00 |
|
|
kijai
|
ac3f285993
|
Update nodes.py
|
2025-03-27 11:17:14 +02:00 |
|
|
kijai
|
163a82c768
|
Update nodes.py
|
2025-03-27 11:14:10 +02:00 |
|
|
kijai
|
7a502dd2c6
|
Update wanvideo_Fun_control_example_01.json
|
2025-03-27 10:37:12 +02:00 |
|
|
kijai
|
1ab1c99bc4
|
Add example for control model
|
2025-03-27 10:07:52 +02:00 |
|
|
kijai
|
d5085d4e87
|
Update nodes.py
|
2025-03-27 09:03:11 +02:00 |
|
|
kijai
|
4a5ed6cb0a
|
Allow Fun Control to work with context windows
|
2025-03-27 01:27:26 +02:00 |
|
|
kijai
|
d20baf0024
|
Add euler/beta, clean scheduler selection code
|
2025-03-26 23:12:15 +02:00 |
|
|
kijai
|
901aff19fd
|
Fix euler and dpm....
|
2025-03-26 22:39:24 +02:00 |
|
|
kijai
|
007fa219ab
|
Update nodes.py
|
2025-03-26 22:23:30 +02:00 |
|
|
kijai
|
94ede80e57
|
Support T2V with Fun InP models
|
2025-03-26 22:00:18 +02:00 |
|
|
kijai
|
921e577ad9
|
Update model.py
|
2025-03-26 18:59:13 +02:00 |
|
|
kijai
|
e5df47a2d3
|
Support Fun-InP control T2V
|
2025-03-26 18:36:08 +02:00 |
|
|
kijai
|
c45d5d3e26
|
Support Fun InP start/end frames
|
2025-03-26 18:17:36 +02:00 |
|
|
kijai
|
da78367bdf
|
Update nodes.py
|
2025-03-26 17:36:59 +02:00 |
|
|
kijai
|
2c2b2c8c54
|
Update nodes.py
|
2025-03-26 17:33:32 +02:00 |
|
|
kijai
|
91f415a127
|
Update nodes.py
|
2025-03-26 17:25:54 +02:00 |
|
|
kijai
|
f08293bf03
|
Update wanvideo_480p_I2V_example_02.json
|
2025-03-26 17:03:40 +02:00 |
|
|
kijai
|
0e0962d6e8
|
support 1.3B Fun Control -model
|
2025-03-26 16:39:27 +02:00 |
|
|
kijai
|
71d02ee0bb
|
smarter zero init
|
2025-03-26 10:56:41 +02:00 |
|
|
kijai
|
b52e5b92bd
|
Update nodes.py
|
2025-03-26 00:14:59 +02:00 |
|
|
kijai
|
d67c96e4b5
|
Update nodes.py
|
2025-03-25 21:30:44 +02:00 |
|
|
kijai
|
d40b28bad6
|
Add CFG-Zero-star
https://github.com/WeichenFan/CFG-Zero-star/
|
2025-03-25 21:19:37 +02:00 |
|
|
kijai
|
a1938107cd
|
Allow splitting self attention as well when using multiple prompts
|
2025-03-25 21:05:08 +02:00 |
|
|
kijai
|
376d4e4557
|
Allow loading comfy-org T5 in the wrapper text encoder loading
|
2025-03-25 19:10:27 +02:00 |
|